A Knowledge-Based Adaptive Event Index Cognitive Model Extraction Method for Document Summarization
A cognitive model, document summarization technology, applied in special data processing applications, natural language data processing, unstructured text data retrieval and other directions, can solve problems such as not being able to reflect text content well
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0032] 1. By analyzing the input document using the invented model method, language features are extracted from the input document;
[0033] 2. Use sentence detection to divide the text of the input document into sentences, use named entity recognition to extract named entities in the text, build a list of named entities, and identify the protagonist and temporality from the list of named entities. The protagonist refers to the subject or sentence of a sentence Noun phrases or pronouns that take on the role of subject in , temporality refers to the time information in each sentence;
[0034] 3. Identify explicit causal relationships in sentences through causal phrases and named entities, while intentional relationships are identified through intentional phrases and named entities. Causal relationships include explicit causal relationships and additional, implicit emotional causal relationships. The intentional relationship refers to the protagonist’s goal and the relationship ...
Embodiment 2
[0039] The context of the causal relationship in the document extracts the causal relationship by using low-ambiguity girju causal phrases from the preprocessed document, and inputs it into the episodic memory knowledge base to determine whether there is such a causal relationship. If there is a causal relationship, the wake-up value will be extracted and the wake-up will be updated. If there is no causal relationship, it will define the arousal value of this relationship, and store or update it in the knowledge base, and create emotional attributes and core effects through the combination of cause and context in the causal relationship, and then update the episodic memory knowledge The causal relationship in the database and the causal relationship knowledge base in the semantic knowledge, thereby creating the context of the causal relationship in the document; the context of the intentional relationship in the document extracts the intentional relationship through the synonym ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More